mnemosyne_memory_ingest

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations are thin (readOnlyHint=false, destructiveHint=false), so the description carries the full disclosure burden, and it delivers the single most important behavioral fact: 'stored permanently and indexed for every future agent to retrieve.' This irreversibility warning is then reinforced in the vault parameter ('Ingest is permanent'), giving agents the clear risk cue they need before calling a write tool. No annotation contradiction arises — a permanent additive write is consistent with destructiveHint=false.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, zero filler: the action and acceptable content types are front-loaded, the permanence trait comes second, and the when-to-use guidance closes. Every sentence earns its place and none repeats what annotations or schema restate, making this an ideal length for agent consumption.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-required-parameter write tool with 100% schema coverage, the description plus schema covers purpose, when to use, target vault semantics, content formatting, and the permanence risk almost completely. The only gap is the operation's response shape (no output schema exists, and the description never says whether the ingest returns a confirmation or identifier), which would help an agent verify successful persistence.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the parameter descriptions are exceptionally rich — the vault parameter explains token formatting, defaults, scoped tokens, and the permanence caveat, while spine_type maps enum values to usage contexts. Per the baseline rule, the schema already does the heavy lifting, and the main tool description adds no parameter-level meaning of its own, so a 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb+resource pair, 'Write a memory into a vault', and enumerates the exact content kinds it accepts (decision, architecture note, debug finding, session summary). The phrase 'stored permanently and indexed for every future agent to retrieve' implicitly differentiates this write tool from the read-only siblings like mnemosyne_memory_query and mnemosyne_memory_ask, so an agent can tell them apart without opening their schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit when-to-use context: 'at the end of a meaningful work session, or whenever a decision is reached that someone will want to recall later.' The vault parameter additionally embeds a prerequisite ('confirm the vault exists with mnemosyne_vault_list before writing anywhere new'). However, it never names read-side or task alternatives (memory_query, memory_ask, todo_add) or states when NOT to use it, so it stops just short of full exclusionary guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.